{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/86618"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/86618","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Hardware for Stress Detection from ECG Signals using Machine Learning","abstract":"M.S.","abstract_html":"M.S.","abstract_has_math":false,"creators":["Bhanushali, Sumukh; 0000-0001-7463-2949"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Sanyal, Arindam","Electrical Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02-21T20:58:52Z","date_published":"2025-02-21T20:58:52Z","updated_at":"2026-07-27T19:05:32Z","subjects":["electrical engineering"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/86618","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sanyal, Arindam","Electrical Engineering"]},{"key":"dc:creator","label":"Author","values":["Bhanushali, Sumukh; 0000-0001-7463-2949"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-02-21T20:58:52Z","2020"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["electrical engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/86618"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["M.S.","A Hardware Implementation of feature extraction and a Machine Learning (ML) system to detect stress from an ECG signal is demonstrated in this work. Only time-domain features have been used instead of frequency or time+frequency domain in order to save the on-chip area and power consumption. Several ML classifiers were used to detect stress from the time-domain features, and out of them, Random Forests (RF) algorithm proved to be the best with 96% accuracy. These time-domain features were also demonstrated on an on-chip Reservoir Computer circuit which resulted in an accuracy of 93%. The software simulations involved training and testing on MATLAB and the hardware implementations for feature extractors were done in Verilog. For testing the on-chip RC, MATLAB was used to inject inputs via a DAQ and the outputs of the chip were probed by a logic analyzer.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Hardware for Stress Detection from ECG Signals using Machine Learning"]}]}],"canonical_facts":{"dc:contributor":["Sanyal, Arindam","Electrical Engineering"],"dc:creator":["Bhanushali, Sumukh; 0000-0001-7463-2949"],"dc:date":["2025-02-21T20:58:52Z","2020"],"dc:description":["M.S.","A Hardware Implementation of feature extraction and a Machine Learning (ML) system to detect stress from an ECG signal is demonstrated in this work. Only time-domain features have been used instead of frequency or time+frequency domain in order to save the on-chip area and power consumption. Several ML classifiers were used to detect stress from the time-domain features, and out of them, Random Forests (RF) algorithm proved to be the best with 96% accuracy. These time-domain features were also demonstrated on an on-chip Reservoir Computer circuit which resulted in an accuracy of 93%. The software simulations involved training and testing on MATLAB and the hardware implementations for feature extractors were done in Verilog. For testing the on-chip RC, MATLAB was used to inject inputs via a DAQ and the outputs of the chip were probed by a logic analyzer.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/86618"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["electrical engineering"],"dc:title":["Hardware for Stress Detection from ECG Signals using Machine Learning"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T19:05:32Z"}